Somesh Jha

39 papers · 2018–2026 · 9 conferences · across top CS/AI conferences

Achievements

+11 more ↓

🌍 Conference Polyglot (9) 🏃 Academic Marathon (7) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (10)

🐝 Cross-Pollinator (10) 🌈 Renaissance Researcher (9) 🗺️ Taxonomy Completionist (35) 🤝 Dynamic Duo (10) 👑 Triple Crown 🔬 Deep Specialist (11) 🔥 Unstoppable (8) 💎 Century Club (38) 🗃️ Keyword Collector (95) ❓ The Questioner (2) ⚡ Prolific Year (5)

Conferences

ICML (12) ICLR (11) NIPS (9) ACL (2) AISTATS (1) ALT (1) EMNLP (1) MLHC (1) WACV (1)

Top co-authors

Jiefeng Chen (10) Xi Wu (8) Jayaram Raghuram (6) Yingyu Liang (6) Jihye Choi (5) Ashish Hooda (4) Kamalika Chaudhuri (3) Nils Palumbo (3) Sanjam Garg (3) Mihai Christodorescu (3)

Research topics

Privacy (1)

Keywords

adversarial robustness (7) adversarial training (4) adversarial learning (3) neural network (3) deep neural network (2) attribution method (2) out-of-distribution detection (2) robust classification (2) learning theory (2) large language model (2) adversarial attack (2) integrated gradient (2) symbolic reasoning (1) uncertainty quantification (1) robust optimization (1) feature selection (1) ensemble learning (1) differential privacy (1) anomaly detection (1) neural network interpretability (1)

Papers

SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification ACL 2026 Validating Mechanistic Interpretations: An Axiomatic Approach ICML 2025 On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark AISTATS 2025 CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts ICLR 2025 AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs ICLR 2025 Can Watermarks be Used to Detect LLM IP Infringement For Free? ICLR 2025 Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks ICLR 2025 On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks ICLR 2024 PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails ACL 2024 Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates ICML 2024 Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection ICML 2024 MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilance MLHC 2024 D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles WACV 2024 Grounding Neural Inference with Satisfiability Modulo Theories NIPS 2023 Stratified Adversarial Robustness with Rejection ICML 2023 Few-Shot Domain Adaptation For End-to-End Communication ICLR 2023 The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning ICLR 2023 Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs EMNLP 2023 Concept-based Explanations for Out-of-Distribution Detectors ICML 2023 Robust and Actively Secure Serverless Collaborative Learning NIPS 2023 Towards Evaluating the Robustness of Neural Networks Learned by Transduction ICLR 2022 Privacy Implications of Shuffling ICLR 2022 A Quantitative Geometric Approach to Neural-Network Smoothness NIPS 2022 Robust Learning against Relational Adversaries NIPS 2022 Overparameterization from Computational Constraints NIPS 2022 Sample Complexity of Robust Linear Classification on Separated Data ICML 2021 A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks NIPS 2021 Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles NIPS 2021 CaPC Learning: Confidential and Private Collaborative Learning ICLR 2021 A General Framework For Detecting Anomalous Inputs to DNN Classifiers ICML 2021 Concise Explanations of Neural Networks using Adversarial Training ICML 2020 On the Need for Topology-Aware Generative Models for Manifold-Based Defenses ICLR 2020 Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models ICML 2020 CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods ICML 2020 Adversarially Robust Learning Could Leverage Computational Hardness. ALT 2020 Attribution-Based Confidence Metric For Deep Neural Networks NIPS 2019 Robust Attribution Regularization NIPS 2019 Analyzing the Robustness of Nearest Neighbors to Adversarial Examples ICML 2018 Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training ICML 2018